design-first-ui-prompting

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill functions as an instructional guide for creating structured text prompts. It does not include executable code, scripts, or shell commands.
  • [SAFE]: No evidence of prompt injection, obfuscation, or data exfiltration was found. The skill contains explicit instructions to avoid external file or script dependencies.
  • [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes untrusted user input and Figma context, but the risk is assessed as safe because it lacks the capabilities to perform dangerous actions.
  • Ingestion points: User requests and Figma frame/context context are used to generate the prompt brief.
  • Boundary markers: The skill uses a rigid Markdown template structure (GOAL, LAYOUT, TYPE, etc.) to organize the output.
  • Capability inventory: No tools, network access, or file-writing capabilities are requested or used.
  • Sanitization: No explicit sanitization of user-provided copy is performed before interpolation into the prompt template.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 06:31 AM
Security Audit — agent-trust-hub — design-first-ui-prompting